Academic Journal
Προβολή σε EDS

Rhythm-aware adaptive spectro-temporal enhancement for underwater acoustic target recognition.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Rhythm-aware adaptive spectro-temporal enhancement for underwater acoustic target recognition.
Συγγραφείς: Liu, Zhengkun1,2 (AUTHOR), Ren, Jiawei1,2 (AUTHOR) renjiawei@hccl.ioa.cn, Xu, Ji1,2 (AUTHOR), Sui, Fusheng2,3 (AUTHOR), Yan, Yonghong1,2 (AUTHOR)
Πηγή: Journal of the Acoustical Society of America. Aug2026, Vol. 160 Issue 2, p1182-1198. 17p.
Θεματικοί όροι: *Adaptive signal processing, *Underwater acoustics, *Deep learning, *Robust statistics, *Signal processing, *Time-frequency analysis
Περίληψη: Passive acoustic target recognition is often constrained by the complex interplay of variable underwater propagation channels and nonstationary target states. While data-driven deep learning models offer exceptional flexibility in feature learning, they are frequently susceptible to overfitting environmental noise and site-specific cues, which undermines their generalization in fluctuating marine conditions. Conversely, methods grounded in physical attributes exhibit superior intrinsic stability across diverse environments but typically lack the comprehensive signal perception and discriminative richness required for sophisticated classification. To bridge this gap, we propose rhythm-aware adaptive spectro-temporal enhancement (RASTE), prioritizing physical interpretability and robustness. Unlike traditional detection of envelope modulation on noise methods that require manual bandpass filter selection and assume signal stationarity, RASTE adaptively extracts rhythmic signatures and maintains efficacy, even under non-stationary conditions, such as pulsed interference. These features are applied as a soft mask to spectrograms to integrate physical priors while preserving the integrity of discriminative features. Experiments on open-source datasets indicate that RASTE serves as a robust and interpretable alternative to baselines. By navigating the performance-interpretability trade-off, RASTE achieves competitive results, particularly in scenarios characterized by pronounced rhythmic structures. [ABSTRACT FROM AUTHOR]
Βάση Δεδομένων: Academic Search Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:asx&genre=article&issn=00014966&ISBN=&volume=160&issue=2&date=20260801&spage=1182&pages=1182-1198&title=Journal of the Acoustical Society of America&atitle=Rhythm-aware%20adaptive%20spectro-temporal%20enhancement%20for%20underwater%20acoustic%20target%20recognition.&aulast=Liu%2C%20Zhengkun&id=DOI:10.1121/10.0044109
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: asx
DbLabel: Academic Search Index
An: 196601554
RelevancyScore: 1452
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1452.42456054688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Rhythm-aware adaptive spectro-temporal enhancement for underwater acoustic target recognition.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liu%2C+Zhengkun%22">Liu, Zhengkun</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ren%2C+Jiawei%22">Ren, Jiawei</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> renjiawei@hccl.ioa.cn</i><br /><searchLink fieldCode="AR" term="%22Xu%2C+Ji%22">Xu, Ji</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sui%2C+Fusheng%22">Sui, Fusheng</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yan%2C+Yonghong%22">Yan, Yonghong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+the+Acoustical+Society+of+America%22">Journal of the Acoustical Society of America</searchLink>. Aug2026, Vol. 160 Issue 2, p1182-1198. 17p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Adaptive+signal+processing%22">Adaptive signal processing</searchLink><br />*<searchLink fieldCode="DE" term="%22Underwater+acoustics%22">Underwater acoustics</searchLink><br />*<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Robust+statistics%22">Robust statistics</searchLink><br />*<searchLink fieldCode="DE" term="%22Signal+processing%22">Signal processing</searchLink><br />*<searchLink fieldCode="DE" term="%22Time-frequency+analysis%22">Time-frequency analysis</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Passive acoustic target recognition is often constrained by the complex interplay of variable underwater propagation channels and nonstationary target states. While data-driven deep learning models offer exceptional flexibility in feature learning, they are frequently susceptible to overfitting environmental noise and site-specific cues, which undermines their generalization in fluctuating marine conditions. Conversely, methods grounded in physical attributes exhibit superior intrinsic stability across diverse environments but typically lack the comprehensive signal perception and discriminative richness required for sophisticated classification. To bridge this gap, we propose rhythm-aware adaptive spectro-temporal enhancement (RASTE), prioritizing physical interpretability and robustness. Unlike traditional detection of envelope modulation on noise methods that require manual bandpass filter selection and assume signal stationarity, RASTE adaptively extracts rhythmic signatures and maintains efficacy, even under non-stationary conditions, such as pulsed interference. These features are applied as a soft mask to spectrograms to integrate physical priors while preserving the integrity of discriminative features. Experiments on open-source datasets indicate that RASTE serves as a robust and interpretable alternative to baselines. By navigating the performance-interpretability trade-off, RASTE achieves competitive results, particularly in scenarios characterized by pronounced rhythmic structures. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=196601554
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1121/10.0044109
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 1182
    Subjects:
      – SubjectFull: Adaptive signal processing
        Type: general
      – SubjectFull: Underwater acoustics
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Robust statistics
        Type: general
      – SubjectFull: Signal processing
        Type: general
      – SubjectFull: Time-frequency analysis
        Type: general
    Titles:
      – TitleFull: Rhythm-aware adaptive spectro-temporal enhancement for underwater acoustic target recognition.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu, Zhengkun
      – PersonEntity:
          Name:
            NameFull: Ren, Jiawei
      – PersonEntity:
          Name:
            NameFull: Xu, Ji
      – PersonEntity:
          Name:
            NameFull: Sui, Fusheng
      – PersonEntity:
          Name:
            NameFull: Yan, Yonghong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 00014966
          Numbering:
            – Type: volume
              Value: 160
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Journal of the Acoustical Society of America
              Type: main
ResultId 1